© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 21083
    Prev
    Next
    INDEX
    Explanations

    phrases related to making modifications or adjustments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to modifications and adjustments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etooth
    -0.73
    bon
    -0.70
    rative
    -0.67
    served
    -0.65
    nces
    -0.64
    icipated
    -0.63
    FIR
    -0.62
    putable
    -0.62
    otal
    -0.62
     Investigator
    -0.60
    POSITIVE LOGITS
     accordingly
    0.82
     resh
    0.80
    wards
    0.79
     favour
    0.75
     favor
    0.72
     altering
    0.72
    changes
    0.71
    into
    0.70
     changes
    0.69
     alterations
    0.69
    Activations Density 0.545%

    No Known Activations